# Qwen3.6 35B A3B

> Compact Qwen3.6 MoE model with a 262K context window. Available serverless and not included in standard Wafer Pass. Optimized for efficient inference with strong reasoning capabilities.

**ID**: `wafer/alibaba-qwen3.6-35b-a3b`  
**Creator**: alibaba  
**Category**: text  
**Context**: 262K tokens  
**Status**: Disabled — no longer routable or listed; kept for history/usage reference.  
**Input**: $0.15/M  
**Output**: $1.00/M  
**Released**: 2026-02-20  
**Web page**: https://anyrouter.dev/model/wafer/alibaba-qwen3.6-35b-a3b

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, reasoning, function-calling, structured-output, streaming

## Usage

**Endpoint**: `POST https://anyrouter.dev/api/v1/chat/completions`

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wafer/alibaba-qwen3.6-35b-a3b",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'
```

## Providers

| Provider | Input | Output |
| --- | --- | --- |
| wafer | $0.15/M | $1.00/M |
| wafer-byok | $0 | $0 |

## Benchmarks

- **GPQA Diamond**: 0.8
- **HLE**: 0.1
- **τ²-Bench Telecom**: 0.9
- **SciCode**: 0.0

## Source

- Upstream docs: https://pass.wafer.ai